Related papers: Weakly Supervised Cross-Modal Learning for 4D Rada…

Estimating 3D scene flow from a sequence of monocular images has been gaining increased attention due to the simple, economical capture setup. Owing to the severe ill-posedness of the problem, the accuracy of current methods has been…

Automotive perception systems are obligated to meet high requirements. While optical sensors such as Camera and Lidar struggle in adverse weather conditions, Radar provides a more robust perception performance, effectively penetrating fog,…

Automotive radar has shown promising developments in environment perception due to its cost-effectiveness and robustness in adverse weather conditions. However, the limited availability of annotated radar data poses a significant challenge…

Weakly supervised object detection (WSOD) aims at learning precise object detectors with only image-level tags. In spite of intensive research on deep learning (DL) approaches over the past few years, there is still a significant…

Holistic 3D scene understanding entails estimation of both layout configuration and object geometry in a 3D environment. Recent works have shown advances in 3D scene estimation from various input modalities (e.g., images, 3D scans), by…

Scene flow prediction is a crucial underlying task in understanding dynamic scenes as it offers fundamental motion information. However, contemporary scene flow methods encounter three major challenges. Firstly, flow estimation solely based…

To reduce the reliance of visible-infrared person re-identification (ReID) models on labeled cross-modal samples, this paper explores a weakly supervised cross-modal person ReID method that uses only single-modal sample identity labels,…

Weakly-supervised object detection (WSOD) models attempt to leverage image-level annotations in lieu of accurate but costly-to-obtain object localization labels. This oftentimes leads to substandard object detection and localization at…

Indirect Time-of-Flight (iToF) cameras are a widespread type of 3D sensor, which perform multiple captures to obtain depth values of the captured scene. While recent approaches to correct iToF depths achieve high performance when removing…

4D radar has received significant attention in autonomous driving thanks to its robustness under adverse weathers. Due to the sparse points and noisy measurements of the 4D radar, most of the research finish the 3D object detection task by…

4D millimeter-wave radar has emerged as a promising sensing modality for autonomous driving due to its robustness and affordability. However, its sparse and weak geometric cues make reliable instance activation difficult, limiting the…

LiDAR is used in autonomous driving to provide 3D spatial information and enable accurate perception in off-road environments, aiding in obstacle detection, mapping, and path planning. Learning-based LiDAR semantic segmentation utilizes…

A critical object detection task is finetuning an existing model to detect novel objects, but the standard workflow requires bounding box annotations which are time-consuming and expensive to collect. Weakly supervised object detection…

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…

Estimation of 3D motion in a dynamic scene from a temporal pair of images is a core task in many scene understanding problems. In real world applications, a dynamic scene is commonly captured by a moving camera (i.e., panning, tilting or…

Light detection and ranging (LiDAR) remote sensing encompasses two major directions: data interpretation and parameter inversion. However, both directions rely heavily on costly and labor-intensive labeled data and field measurements, which…

Integrating different representations from complementary sensing modalities is crucial for robust scene interpretation in autonomous driving. While deep learning architectures that fuse vision and range data for 2D object detection have…

Weakly-supervised salient object detection (WSOD) aims to develop saliency models using image-level annotations. Despite of the success of previous works, explorations on an effective training strategy for the saliency network and accurate…

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data. Our method is based on invariant instance feature learning but is tailored for…

Using 3D point clouds in odometry estimation in robotics often requires finding a set of correspondences between points in subsequent scans. While there are established methods for point clouds of sufficient quality, state-of-the-art still…